Skill: Hive-Commander-Kernel (Harness-V2)
1. Execution Pipeline
Phase 1: Sub-task Matrix Generation
Identify the operational mode and map user intent into a 5-node matrix. Assign specialized identities to each node via metadata-driven prompting.
Phase 2: Session Extraction Protocol
Mandatory extraction of
api_key,
base_url, and
model_id. These parameters
MUST be injected into the worker configuration to ensure parity with the master session.
Phase 3: Configuration Serialization
Construct
~/.openclaw/swarm_tmp/task_config.json adhering to the following Schema:
{
"session": {"api
key": "str", "baseurl": "str", "model": "str"},
"workers": [{"id": "int", "role": "str", "prompt": "str", "query": "str"}]
}
Phase 4: Hardware-Accelerated Dispatch
Invoke
python3 ~/.openclaw/skills/hive-commander/executor.py for parallel execution.
- * Timeout Handling: 120s per node.
- Failure Policy: Revert to synchronous serial execution on error.
Phase 5: Synthesis & Conflict Audit
Final aggregation of
worker_*.md outputs. Perform logical de-confliction to ensure the final report is devoid of internal contradictions.
2. Hard Constraints
- * Parallelism: Fixed at 5 Workers.
- Context Isolation: Workers SHALL NOT share context during the execution phase.
- Pathing: Strictly enforced absolute paths within
~/.openclaw/.
技能：蜂群指挥官-内核（Harness-V2）
1. 执行流水线
阶段一：子任务矩阵生成
识别操作模式，将用户意图映射至5节点矩阵。通过元数据驱动的提示词为每个节点分配专业身份。
阶段二：会话提取协议
强制提取api
key、baseurl和model_id。这些参数
必须注入工作节点配置，以确保与主会话的一致性。
阶段三：配置序列化
构建~/.openclaw/swarm
tmp/taskconfig.json，遵循以下架构：
{
session: {api
key: 字符串, baseurl: 字符串, model: 字符串},
workers: [{id: 整数, role: 字符串, prompt: 字符串, query: 字符串}]
}
阶段四：硬件加速调度
调用python3 ~/.openclaw/skills/hive-commander/executor.py进行并行执行。
- * 超时处理： 每节点120秒。
- 失败策略： 出错时回退至同步串行执行。
阶段五：综合与冲突审计
最终聚合worker_*.md输出。执行逻辑去冲突，确保最终报告不存在内部矛盾。
2. 硬性约束
- * 并行度： 固定为5个工作节点。
- 上下文隔离： 工作节点在执行阶段不得共享上下文。
- 路径规范： 严格遵循~/.openclaw/内的绝对路径。
